LexiconVLA: Learning Reusable Atomic Action Codebooks for Unseen Tasks
cs.RO
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Genie: Generative Interactive Environments
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- GR-3 Technical Report
- VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
- RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
- Mean-Flow based One-Step Vision-Language-Action
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
- Gaussian Error Linear Units (GELUs)
- LoRA: Low-Rank Adaptation of Large Language Models
- Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
- 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- BridgeVLA++: A Data-Efficient, Generalizable, and Memory-Augmented Vision-Language-Action Framework for 3D Manipulation
- Flow Matching for Generative Modeling
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- DINOv2: Learning Robust Visual Features without Supervision
- FAST: Efficient Action Tokenization for Vision-Language-Action Models
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving